© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 42284
    Prev
    Next
    INDEX
    Explanations

    specific library and framework references in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĪãĥª
    -0.07
     çĶŁåij½åij¨æľŁåĩ½æķ°
    -0.07
     cudaMemcpy
    -0.07
    kola
    -0.07
    OffsetTable
    -0.06
    umbed
    -0.06
    kontakte
    -0.06
    nÃŃ
    -0.06
    UrlParser
    -0.06
    fax
    -0.06
    POSITIVE LOGITS
    doch
    0.07
     Hitch
    0.06
    pedia
    0.06
    arine
    0.06
    ffd
    0.06
    _FD
    0.06
    uluk
    0.06
    dea
    0.06
    ichi
    0.05
    ãģ¾ãģļ
    0.05
    Activations Density 0.057%

    No Known Activations